BenchLeader

Qwen3.7 Max

Reasoning effort
Quality#42 of 351
59.8Index
Top quarter
+10.1 on the median
Price#209 of 262
$3.75per 1M tokens
Dearest quarter
4.2× the median
Speed#36 of 215
145tokens/s
Top quarter
1.8× the median
Value#204 of 262
15.9points per $
Bottom quarter
0.3× the median

Better value: GPT-5.6 Luna scores 58.1 for $0.450/M, 88% cheaper.

12 cheaper ranked models score higher: Gemini 4 Hydrogen (63.6, $3.00), GPT-6.1 Terra (63.2, $2.00), Gemini 3.5 Flash (62.4, $3.38) and 9 more.

As of 19 Nov 2026, Qwen3.7 Max by Alibaba scores 59.8 on the BenchLeader Index (top 100 of 631 ranked configurations), with its best results in instruction following (78) and weakest in agents & tools (49). API pricing: $2.50 per 1M input tokens and $7.50 per 1M output tokens ($3.75 blended at 3:1), list price on 19 Nov 2026. It streams about 150 tokens/s (Artificial Analysis). Released 19 May 2026.

Key facts (as of 19 Nov 2026)

  • Qwen3.7 Max API pricing: $2.50 per 1M input tokens and $7.50 per 1M output tokens ($3.75 blended at 3:1) (list price, 19 Nov 2026).
  • Qwen3.7 Max streams about 150 tokens/s (Artificial Analysis, 19 Nov 2026).
  • Qwen3.7 Max was released on 19 May 2026 (Alibaba).

In detail. Qwen3.7 Max is an Alibaba proprietary reasoning model, released 19 May 2026. Its best configuration ranks #100 of 631 on the BenchLeader Index at 59.8 ±4.3, in the upper half. The ± is the point: 232 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (78) and lowest in agents & tools (49). At $3.75 per million tokens blended it is pricier than most ranked models. Output speed of 145 tokens per second puts it in the fastest quarter, with a first answer in 14.1 s. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 18 Nov 2026.

Blended price
$3.75/M
$2.50 in · $7.50 out
via Artificial Analysis
Output speed
145 tok/s
measured by Artificial Analysis
First answer
14 s
first token 1.18 s
Context
1M
via models.dev
Accepts
Text
via models.dev, OpenRouter
Full answer
31 s
last measured 13 Nov 2026
Cost per task
–
Tokens per task
–
Released
19 May 2026
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index60
  2. Reasoning64
  3. Coding59
  4. Agents & tools49
  5. Maths58
  6. Knowledge61
  7. Instruction following78
  8. Human preference56
  9. Long context64

Embed this rank

More badge styles
[![Qwen3.7 Max on BenchLeader: #42 overall](https://www.benchleader.com/badge/qwen3-7-max.svg?style=compact)](https://www.benchleader.com/models/qwen3-7-max)

Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.

Get an email when Alibaba ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

Versions

Alibaba has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Qwen3.8 Max3 Aug 202659.0#118
Qwen3.7 Maxthis page19 May 202659.8#100
Qwen3.6 Max20 Apr 202662.0#61
Qwen3.5 Max–––

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.

EffortIndexRankSpeedFirst answerChat reply costCategories
no reasoning––145 tok/s14 s$0.0033
xhigh––145 tok/s14 s$0.0033
not statedbest59.8#100145 tok/s14 s$0.0033Agents & tools 49 · Coding 59 · Human preference 56 · Instruction following 78 · Knowledge 61 · Long context 64 · Maths 58 · Reasoning 64

How its index has moved

8 Sep 2026 to 19 Nov 2026
535966

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarkno reasoningnot statedSourceTrend
GPQA Diamondeffort not stated–90.9%#42Epoch AI Benchmarking Hub
SimpleBencheffort not stated–70.4%#26SimpleBench
Arena Hard Promptseffort not stated–1494#47Arena (LMArena)
LiveBench 1.0 Reasoningnot in indexeffort not stated–83.3%#43LiveBench
GPQA Diamond (AA)not in indexeffort not stated–92.3%#36Artificial Analysis
Humanity's Last Exam (AA)not in indexeffort not stated–40.5%#96Artificial Analysis
GPQA Diamond (Vals)not in indexeffort not stated–90.2%#25Vals AI
CritPtnot in indexeffort not stated–13.4%#114Artificial Analysis
Arena Expertnot in indexeffort not stated–1508#36Arena (LMArena)
Chess Puzzlesnot in indexeffort not stated–27.0%#79Epoch AI Benchmarking Hub
Mystery Game Puzzlesnot in index26.0%#4932.0%#36Epoch AI Benchmarking Hub
LMCAnot in indexeffort not stated–44.0%#102Epoch AI Benchmarking Hub
DTBenchnot in indexeffort not stated–92.3%#76Epoch AI Benchmarking Hub

Knowledge

Benchmarkxhighnot statedSourceTrend
SimpleQA Verifiedeffort not stated–55.8%#27Epoch AI Benchmarking Hub
LiveBench 1.0 Data Analysisnot in indexeffort not stated–71.8%#47LiveBench
MMLU-Proeffort not stated–89.3%#12Vals AI
LegalBencheffort not stated–84.9%#28Vals AI
CorpFineffort not stated–63.7%#42Vals AI
TaxEvaleffort not stated–75.3%#19Vals AI
Excel Modeling Benchmarknot in indexeffort not stated–57.0%#43Vals AI
MedCodenot in indexeffort not stated–38.8%#68Vals AI
MedScribenot in indexeffort not stated–79.4%#62Vals AI
DrugDiscoveryBenchnot in index29.3%#25–Scale AI SEAL
EBR-benchnot in indexeffort not stated–9.5%#29Epoch AI Benchmarking Hub

Instruction following

Benchmarknot statedSourceTrend
LiveBench Languagenot in index79.7%#33LiveBench
LiveBench Instruction Followingnot in index74.0%#14LiveBench
IFBench80.5%#7Artificial Analysis
Arena Instruction Followingnot in index1466#47Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1474#44Arena (LMArena)
EQ-Bench 41100#27EQ-Bench
Arena Creative Writingnot in index1440#63Arena (LMArena)
Arena Multi-turnnot in index1481#40Arena (LMArena)
Arena Longer Queriesnot in index1491#28Arena (LMArena)

Long context

Benchmarknot statedSourceTrend
AA-LCR v1.179.0%#120Artificial Analysis
MLCRnot in index14.4%#115Artificial Analysis

Composite

Benchmarknot statedSourceTrend
Epoch Capabilities Indexnot in index154.6#48Epoch AI Benchmarking Hub
LiveBench 1.0not in index73.1%#47LiveBench
AA Intelligence Index v4.3.2not in index29.5#134Artificial Analysis
AA Progress Index v1not in index293.8#136Artificial Analysis

API pricing: where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
Alibaba Cloud Int.67 tok/s1.17 s$1.48$4.421M–

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.500 per 1M. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0033$0.002716.1 s
Summarize a 30-page report12,000 / 600$0.035$0.01718.2 s
Code edit6,000 / 1,500$0.026$0.01724.4 s
Agentic coding session60,000 / 4,000$0.180$0.09041.6 s
Structured extraction2,000 / 200$0.0065$0.003515.4 s

More from Alibaba

New this month

Compare Qwen3.7 Max with…

See also

Embed or cite

Show where Qwen3.7 Max ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.

[![Qwen3.7 Max on BenchLeader: #42 overall](https://www.benchleader.com/badge/qwen3-7-max.svg)](https://www.benchleader.com/models/qwen3-7-max)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 19). Qwen3.7 Max on the BenchLeader Index (method v1.5) [Data set]. Retrieved November 19, 2026, from https://www.benchleader.com/models/qwen3-7-max

BibTeX:

@misc{benchleader_qwen3_7_max_20261119,
  author       = {{BenchLeader}},
  title        = {{Qwen3.7 Max on the BenchLeader Index (method v1.5)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/qwen3-7-max}},
  note         = {Data as of 2026-11-19}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are Qwen3.7 Max's benchmark scores?
As of 19 Nov 2026, Qwen3.7 Max scores 59.8 ±4.3 on the BenchLeader Index, top 100, strongest in instruction following (78) and weakest in agents & tools (49). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Qwen3.7 Max rank?
Qwen3.7 Max is #100 of 631 ranked configurations on 19 Nov 2026 (top 100). 232 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 71.5.
How much does Qwen3.7 Max cost per 1M tokens?
As of 19 Nov 2026, Qwen3.7 Max costs $2.50 per 1M input tokens and $7.50 per 1M output tokens, $3.75 blended (three input tokens per output token).
Is Qwen3.7 Max better than Gemini 3.8 Flash?
As of 19 Nov 2026, Gemini 3.8 Flash (medium) and Qwen3.7 Max are neck and neck on quality (59.8 vs 59.8 on the BenchLeader Index, inside the ±6.6 margin of error), and Gemini 3.8 Flash (medium) costs 2.5× less, which makes it the better buy for most workloads. The head-to-head page has the benchmark-by-benchmark detail.
When was Qwen3.7 Max released?
Alibaba released Qwen3.7 Max on 19 May 2026. BenchLeader has results for it at 3 reasoning-effort settings.

Data as of 19 Nov 2026. Compare these configurations.

Cite as: BenchLeader, “Qwen3.7 Max: benchmarks, pricing, speed and rank”, data as of 19 Nov 2026, https://www.benchleader.com/models/qwen3-7-max.